Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1066 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.4186. Min Act: -0.0000

Data Index: 813793 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.4183. Min Act: -0.0000

Data Index: 686072 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.3630. Min Act: -0.0000

Data Index: 159523 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.4702. Min Act: -0.0000

Data Index: 950719 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2183. Min Act: -0.0000

Data Index: 721422 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.1636. Min Act: -0.0000

Data Index: 429289 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.2604. Min Act: -0.0000

Data Index: 357464 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.0185. Min Act: -0.0000

Data Index: 783620 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.0721. Min Act: -0.0000

Data Index: 277162 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.4702. Min Range: -1.4702

Max Act: 1.0107. Min Act: -0.0000

Data Index: 733545 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9495. Min Act: -0.0000

Data Index: 507356 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9498. Min Act: -0.0000

Data Index: 687629 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.8780. Min Act: -0.0000

Data Index: 94402 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9030. Min Act: -0.0000

Data Index: 400385 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9319. Min Act: -0.0000

Data Index: 244499 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9001. Min Act: -0.0000

Data Index: 370591 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.8684. Min Act: -0.0000

Data Index: 977608 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1262510 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1333907 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.4702. Min Range: -1.4702

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1186238 (C4 (Web Text))

Max Activating Token Index: 157